10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Redefining the Bayesian Information Criterion for Speaker Diarisation

Themos Stafylakis, Vassilis Katsouros, George Carayannis

Athena Research Center, Greece

A novel approach to the Bayesian Information Criterion (BIC) is introduced. The new criterion redefines the penalty terms of the BIC, such that each parameter is penalized with the effective sample size is trained with. Contrary to Local-BIC, the proposed criterion scores overall clustering hypotheses and therefore is not restricted to hierarchical clustering algorithms. Contrary to Global-BIC, it provides a local dissimilarity measure that depends only the statistics of the examined clusters and not on the overall sample size. We tested our criterion with two benchmark tests and found significant improvement in performance in the speaker diarisation task.

Full Paper

Bibliographic reference.  Stafylakis, Themos / Katsouros, Vassilis / Carayannis, George (2009): "Redefining the Bayesian information criterion for speaker diarisation", In INTERSPEECH-2009, 1051-1054.